{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UK2MIMUXYLAALSALDQG2RKB5YT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"63b2223246a4d5c943e2720dcece14a03aef28375d68db2127191734588d65a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T14:38:01Z","title_canon_sha256":"9edef50804b20e424121923ce45cb2ab389e31ade076482b332bae5c0d10f87c"},"schema_version":"1.0","source":{"id":"2501.01834","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01834","created_at":"2026-07-05T10:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01834v3","created_at":"2026-07-05T10:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01834","created_at":"2026-07-05T10:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"UK2MIMUXYLAA","created_at":"2026-07-05T10:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"UK2MIMUXYLAALSAL","created_at":"2026-07-05T10:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"UK2MIMUX","created_at":"2026-07-05T10:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:feb2bc42f3bcc7d1bfcf82362b6a559ff33f94b29cde9cb84e1cf41a04daa9be","target":"graph","created_at":"2026-07-05T10:05:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.01834/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image captioning is a critical task at the intersection of computer vision and natural language processing, with wide-ranging applications across various domains. For complex tasks such as diagnostic report generation, deep learning models require not only domain-specific image-caption datasets but also the incorporation of relevant general knowledge to provide contextual accuracy. Existing approaches exhibit inherent limitations: specialized models excel in capturing domain-specific details but lack generalization, while vision-language models (VLMs) built on large language models (LLMs) leve","authors_text":"Bin Dong, Pu Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T14:38:01Z","title":"MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01834","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:38866db79c47cd6c49cbd4cdb2c67f0ec02d881bfd658b076a4f2ed2db86ffdc","target":"record","created_at":"2026-07-05T10:05:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"63b2223246a4d5c943e2720dcece14a03aef28375d68db2127191734588d65a1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T14:38:01Z","title_canon_sha256":"9edef50804b20e424121923ce45cb2ab389e31ade076482b332bae5c0d10f87c"},"schema_version":"1.0","source":{"id":"2501.01834","kind":"arxiv","version":3}},"canonical_sha256":"a2b4c43297c2c005c80b1c0da8a83dc4ccad3f8beb59f4224a85f63e1c5ee1df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2b4c43297c2c005c80b1c0da8a83dc4ccad3f8beb59f4224a85f63e1c5ee1df","first_computed_at":"2026-07-05T10:05:47.623471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:47.623471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"McQ0pDrVWoUWntzIO3wdx7GAW2iUN5RrcRJs8J5KuOvQgR/qgEP82yNM3UoHQNWAqTpw4kYsHQYZO7vkqO47Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:47.623944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01834","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38866db79c47cd6c49cbd4cdb2c67f0ec02d881bfd658b076a4f2ed2db86ffdc","sha256:feb2bc42f3bcc7d1bfcf82362b6a559ff33f94b29cde9cb84e1cf41a04daa9be"],"state_sha256":"8c609bebaea3d645318de7f54c90fdae6a1584251d7096232488a5dab3956df8"}